Mobile　Edge　Computing　(MEC)　is　a　supplement　to　traditional　cloud　computing.　Its　characteristics　are　low　latency　and　high　reliability,　and　it　will　be　widely　used　in　the　future.　However,　their　dense　deployment　pattern　raises　a　big　concern　on　the　system-wide　energy　consumption.　Dynamic　power　management　(DPM)　method　is　an　important　method　to　solve　energy　consumption　problems,　it　saves　energy　by　shutting　down　servers　in　the　EDC　that　are　idle　or　have　low　utilization.　In　this　paper,　a　DPM　method　based　on　reinforcement　learning　was　proposed,　it　achieves　the　trade-off　between　EDC　service　performance　and　energy　consumption　by　learning　the　global　optimal　dynamic　timeout　threshold　power　management　strategy　by　trial　and　error.　Experiments　have　shown　that　the　proposed　method　saves　no　less　than　6.35%　energy　consumption　compared　to　the　expert-based　method.　©　2018　IEEE.